Home

Welcome to TR's NAI Research Wiki!

Here you will find mainly two things:

• A record of my own findings and thoughts on research methodology from tinkering with Novel AI
• An archive of community research findings from the #community-reserach channel in the NAI discord for the period of 14/06/2021 to 04/07/2021.

"I am new to Novel AI and just found this page"

I do not have much to offer you at the moment, sorry. Most things in this wiki are outdated. This wiki will be mostly of use for community researcher.

If you are looking for advice on using NAI with methods that are known and confirmed to work use the NAI Knowledge Base!

Log of TR's research findings

Nothing here yet for current models. I am still cleaning up this wiki, and then will see what kind of research I find interesting. I currently do have not a lot of time to commit to Novel AI experiments, so expect things to go slow here.

In the meantime, there are some old sections that should still be relevant for newer NAI models. Feel free to poke around my list of Novel AI tools, as well as have a look at my notes on research methodology.

Archive of NAI community research findings (14/06/2021 to 04/07/2021)

During the early days of NovelAI, I tried to pull together the key findings from people's research efforts in #community-research in the NAI discord.

For the most part this was done by working through the chat log, skimming the messages from the date of open beta (14/06), trying to summarize what look like the key findings. These findings concern mostly Sigurd v2 and Sigurd v3, so it is unclear how valid those are for newer NAI models. Findings and observations for older NAI models do not necessarily carry over to newer ones. Also, these observations are not to be taken as gospel - confirming other people's observations from using NAI is hard and time-consuming! So treat most things in the archives as very preliminary findings! In the few cases, where more extensive testing was done, and anecdotal observations held up, it is noted.

I think the most useful use of this archive should be to serve as inspiration for your own experimentation with newer models. Some stuff in there might work for all models, some of it might not, some of it might have been in mistake and was never true for any model. Either way, hopefully by trying things out with the newer models, we can all learn a bit more.